Papers

Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on prior knowledge, cohort catalogues, and manual literature searches. We developed a complementary question-driven framework that searches relevant scientific literature and extracts explicit cohort names. Methods: The framework first generates multiple PubMed queries from configurable vocabularies and templates and retrieves the resulting scientific literature automatically through the PubMed API. A large language model then screens the retrieved titles and abstracts and extracts explicit cohort names using a prompt tailored to the research question. The extracted names are deduplicated with human review. Configurable code, prompts, and example outputs are available at https://gitlab.rz.uni-frankfurt.de/cap_molgenlab/literature-cohort-discovery. Evaluation: As a use case, we applied the framework to youth aggression genetics. From 5,400 generated PubMed queries, the framework retrieved 5,254 unique records and identified 188 candidate cohorts. Manual screening using predefined criteria, including participant age and genetic-data availability, retained 44 eligible cohorts. Automated LLM-based name extraction was within the agreement range of human annotators. We also searched four established cohort catalogues using the same research question. Their combined results contained 27 of the 44 eligible cohorts, while 17 were not returned by any cohort catalogue search. Conclusion: The framework converts research-question-specific vocabulary into screenable cohort inventories via a large, automated literature search. It can be adapted across populations, phenotypes, data modalities, and study designs, and provides a literature-based complement to curated cohort catalogues.

Generative search engines (GSEs) answer user queries directly from crawled web content. The capture of value from the corpus without a visit returned to the source (we call this capture extraction) diverts the traffic that finances content production. In response, publishers may restrict crawler access to their websites. In this paper, we model the crawlable corpus as a common-pool resource: the crawlable commons. It is described by three quantities: volume, average quality, and lifetime. Under two types of responses of publishers we prove that extraction degrades all three at once: publishers opt out, renewal loses its funding, and content becomes more perishable. After a given erosion threshold, the corpus goes extinct. A myopic GSE can cross this threshold, a long-run oriented GSE stays below it. We extend our model to several competing engines and prove, under a concavity condition on the steady-state value of the commons, that the symmetric equilibrium extraction rate is nondecreasing in their number and converges to the threshold. Adding users who strictly prefer direct answers, the assumption most favorable to extraction, we prove that the socially optimal extraction rate lies strictly below the erosion threshold, and no higher than the single engine's sustainable optimum. Finally, we discuss seven survival mechanisms.

Retrieval-augmented generation (RAG) systems rely on retrieval modules to ground large language model (LLM) outputs. LLM-based query expansion enriches retrieval with document-like passages, but evaluations of hybrid retrieval often fuse fixed top-L prefixes of dense and sparse rankings. Because L controls cross-channel contributions and ranking access, it can alter measured expansion gains. We therefore evaluate complete-list effectiveness and record per-channel replay stopping depths required to certify the ordered top-K. This changes the design: because both rankings determine the fused result, their query constructions should be coordinated rather than designed independently. We present DESA (Dense Expansion and Sparse Anchoring), which shares generated references across channels but specializes their integration. Orthogonal residual expansion adds new semantic directions to the dense query, whereas score-product anchoring reorders the original sparse support without admitting expansion-only matches. The same references thus play complementary roles: Dense expands; Sparse anchors. Across seven BEIR datasets, DESA improves nDCG@10 and Recall@20 over the unexpanded query by 3.82% and 2.38%, while reducing dense and sparse replay stopping depths by 36.90% and 36.56%.

Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms. Items lose relevance through two primary mechanisms: supersession, where emerging updates render prior coverage stale, and relevance decay, where an item's informational value naturally diminishes over its lifecycle. Traditional countermeasures serve as crude proxies: age cutoffs poorly reflect actual relevance loss, while engagement heuristics rely on lagging signals, broadly exposing users to stale content before the system adapts. We present SDF (Supersession-Decay Filtering), a staleness filtering system fully deployed in Google Discover, a personalized recommendation feed with hundreds of millions of daily and billions of monthly active users. SDF targets both mechanisms with complementary filters, each powered by a learned model: a relational staleness model that detects supersession between item pairs, and a predicted traffic ratio (PTR) model that forecasts relevance decay from the item's content, trained on lifetime visit traffic. Applied via disjunction upstream of the ranking stage, SDF prunes stale candidates, measurably reducing downstream serving costs. Online experiments demonstrate that these filters significantly reduce the prevalence of stale content while improving user engagement. Over a two-year production deployment, user-filed staleness reports (in-product user feedback) declined by 54.9% relative to the pre-deployment baseline, establishing SDF as a robust and scalable paradigm for resolving content staleness at industrial scale.

Osteoarthritis (OA) is a progressive chronic joint disease resulting in a breakdown of articular cartilage and bone when damaged joint tissues are not able to normally repair themselves. The aim of this pilot research study is to understand the pain severity for OA from patients' primary care Electronic Medical Records (EMR), both from the structured medical data and the unstructured chart note data using information extraction, natural language processing and machine learning techniques. We propose SPaDe, a Synonym-based Pain level Detection tool to categorize patients into having mild or moderate-to-severe pain to understand diagnosis and treatment methods based on only the pain related expressions in the unstructured chart note. Expressions are subjective, objective, and influenced by cultural background and demography which poses a difficult challenge. Therefore, we improve the model by incorporating the medication information from the structured EMR data and pain scale related information from the chart note to propose an integrated pain level detection tool for OA called PLeDO. With the help of human labeled gold standard data, we demonstrate that both SPaDe and PLeDO can detect mild and moderate-to-severe pain from the EMR data to analyze and potentially improve the quality of care in primary care setting.

Each year, the European Migration Network (EMN) country factsheets deliver an overview of key migration and international protection developments within all EMN Member States and observer countries. The factsheets include both a textual component and a visual component. In this paper, we introduce a curated dataset of the textual component of these reports over 35 countries and 13 years (2012-2024.) The dataset was created to facilitate European-level research on migration policies and developments, and promote the use of reliable sources about migration in data science and media research, particularly at a time when the spread of online misinformation about migration constitutes a serious issue. The dataset transforms the original document texts into a tabular format, with columns corresponding to country, year, section, subsection, content, and harmonized title section. We illustrate the value of the dataset with concrete analyses and propose envisioned applications and uses of the dataset. The dataset is accessible through a DOI link.

Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across text, layout, charts, and visual structures. Recent efforts toward finer-grained supervision primarily rely on textual descriptions or localized visual regions as evidence proxies. However, such supervision signals may either overlook complex visual structures or provide incomplete and inaccurate representations of the underlying evidence. To address these limitations, we propose ConceptFormer, a latent concept representation learning framework for visual document retrieval. ConceptFormer models query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance, without requiring either textual intermediate representations or direct reliance on raw visual annotations. During training, ConceptFormer employs a strong vision-language model to dynamically determine the number of latent concept tokens and uses these concepts as an intermediate representation to bridge the semantic gap between queries and documents, thereby guiding the learning of the embedding space. Experiments on diverse visual document retrieval benchmarks demonstrate that ConceptFormer achieves 16.7% and 22.1% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively. Further analysis reveals that latent concepts effectively connect localized visual evidence with semantic relevance, enabling the retriever to capture both fine-grained textual cues and complex document-level visual structures while preserving strong retrieval alignment. Codes and data are available at https://github.com/Neuir/ConceptFormer.

Scientific papers contain multiple searchable facets such as background, methods. However, many paper retrieval benchmarks merely evaluate individual query-paper relevance, while overlooking other facets of the same paper. To bridge this gap, we introduce MAPLE, an expert-validated benchmark for multi-aspect, full-paper retrieval that evaluates whether retrievers can consistently recover the same paper from queries targeting its motivation, method, and experimental findings. MAPLE contains 2,095 queries about recent ML and NLP papers, grounded in both textual and multimodal content. We further propose MAPLE-Synth, a retrieval-based in-context learning pipeline that leverages OpenReview discussions and human-written query exemplars to generate realistic queries reflecting researchers' interests in different aspects of a paper. Our expert validation shows that these queries are comparable in realism to human-written queries and highly relevant to the target papers. Experiments across lexical, scientific-domain, general-purpose text, and multimodal retrievers reveal a substantial gap between retrieving a paper from any one aspect and retrieving it from all aspects: the strongest model achieves 98.1% AnyAspect@20 but only 15.7% AllAspect@20. Experiment/result queries and table-referenced queries are particularly difficult across retrievers. Although multi-chunk aggregation improves multi-aspect paper retrieval, considerable failures persist. MAPLE provides a testbed for evaluating and developing retrievers that represent scientific papers more comprehensively.

Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making time-to-index a first-order systems concern. We present NeuRoute, a learned hashing index that turns short binary codes into an effective routing primitive for large-scale vector search. NeuRoute trains a lightweight neural network encoder with a selective similarity-preserving objective to produce well-balanced binary addresses. During construction, NeuRoute organizes vectors into buckets by their codes and performs bucket-local clustering in the encoder's low-dimensional space to form centroids. At query time, NeuRoute exploits the encoder logits as an uncertainty signal: it uses deviation-to-threshold scores to prioritize uncertain-bit perturbations for query-adaptive multi-bucket probing, scores bucket-local centroids by their distances to the query to form a compact candidate cluster set, and applies centroid-stage gating with heap-quality-driven early stopping to prune low-value clusters before exact refinement. On billion-scale benchmarks, NeuRoute achieves strong accuracy-throughput trade-offs with fast index construction: on BigANN-1B it reaches $90.3\%$ Recall@10 at 2,414 QPS and is $1.7\times$ faster than OPQ+IVF-PQ (refine) at comparable accuracy, while completing end-to-end training+construction in under an hour on both BigANN-1B and Deep1B-1B. These results show that logit-guided neural routing can make hashing competitive as a lightweight ANN indexing framework at billion scale. Source code and artifacts are available at https://github.com/XingqiaoWang/NeuRoute.

Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surface behavioral signals spanning distinct behavioral domains. We present SAGA, a generative action embedding model that encodes multi-surface user interaction sequences across a Financial Service organization's ecosystems, from checkout, peer-to-peer (P2P) transactions, in-app engagement, email to account actions, into a unified user representation for downstream recommendation tasks. Central to SAGA is a per-field tokenization schema that decomposes each action event into multiple field-level tokens (e.g. product, interaction, surface), enabling field-level attention and per-field training objectives that fused single-token approaches cannot support. Through an offline ablation study on loss formulation, tokenization granularity and training data scope, we isolate the contribution of each design choice. A downstream model integrated with SAGA-generated user embeddings delivers the strongest overall click and conversion lift across diverse downstream touchpoints, compared to all ablated and alternative architectures.

Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning about interventions, mechanisms, harms, evidence, and uncertainty. We propose a reproducible, graph-centered evaluation framework for intervention-oriented LLM behavior in healthcare and stress-test it in a cardiovascular pilot. The framework has four components: (i) a domain causal knowledge graph in which assertions are first-class, provenance-preserving nodes with stable identifiers; (ii) a scenario-conditioned subgraph extraction step that, given any clinical scenario, retrieves the relevant reified-assertion subgraph; (iii) four controlled grounding conditions that vary how the retrieved subgraph is composed into the model's context (ungrounded C1, knowledge-graph C2, causal-graph C3, integrated C4); and (iv) an automated scoring pipeline, anchored on assertion identifiers, that computes intervention accuracy, and other evaluation measures on a single pass. To test the framework, we built a category-balanced scenario generator across eight reasoning failure modes and instantiated it on a cardiovascular graph. The metric panel discriminates conditions along interpretable, non-redundant axes: C4 obtains the strongest causal edge F1 (0.838), adverse-effect F1 (0.833), evidence accuracy (0.738), and unsupported claim rate (0.114), while C1 obtains the highest raw intervention accuracy (0.948) with no measurable causal or evidential grounding.

Crowd counting must recover reliable local density under severe variations in perspective, head scale, occlusion, and background clutter. Although modern counting objectives provide strong spatial supervision, many multi-level decoders still use spatially invariant feature fusion and apply one receptive-field pattern to every location. We propose DCA-MoE, a framework that makes both decisions content dependent while retaining a frozen DINOv3 encoder. Spatially Adaptive Layer Fusion (SALF) predicts position-wise weights over four aligned backbone features, and Density-Routed Multi-Receptive-Field Experts (DR-MoE) assigns each location a soft mixture of local, mid-range, and large-context residual experts. An EBC-style head reconstructs block density, while DMCount supervision and an auxiliary routing-balance term train the decoder without updating the backbone. On the NWPU-Crowd validation split, the strongest paired configuration, based on DINOv3 ViT-L/16, obtains 31.7 MAE and 72.2 RMSE; the matched ViT-B/16 full model obtains a paired 32.2/75.9. Cross-dataset results remain mixed, and several component baselines currently report independently selected minima from a single seed. The evidence therefore supports the feasibility of spatially adaptive fusion and routing, while broader paired and multi-seed evaluation remains necessary for causal attribution.

In this paper, we analyze the reasoning trajectories of a variety of DRAs and show that existing agents often suffer from reasoning stagnation: the majority of iterations contribute little or no improvement to final performance, while agents lack awareness of their trajectories and are therefore ineffective at adapting their search strategies or determining when to terminate. To address this issue, we introduce a set of unsupervised signals and a Retrieval-Aware Agent Controller (RAAC), which assists the agent in selecting optimal actions at each stage of the research process. RAAC incorporates key information retrieval principles, namely search novelty and information coverage, resulting in more effective reasoning trajectories that improve overall performance while reducing unnecessary iterations, and consequently cost and latency. Specifically on BrowseComp-Plus and across a large set of DRAs, adding RAAC reduces the number of search calls by an average of 14, significantly improves the best-performing DRA on recall and accuracy, and achieves an accuracy gain of up to 10% (3% on average).

As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottleneck from idea generation to idea evaluation. Existing evaluators mainly rely on parametric LLM knowledge or unstructured retrieval, producing judgments that lack the experience-grounded reasoning used by human instructors. To address this, we propose DeepInstructor, an agentic framework that formulates idea evaluation as reasoning over structured scholarly experience. DeepInstructor constructs an Experience Graph from 58,607 peer reviews and employs a ReAct-based agent to retrieve dimension-specific evidence for traceable evaluation. We further introduce DeepInstruct, a dataset with controlled pairwise comparisons across novelty, significance, and feasibility. Experiments show that DeepInstructor substantially outperforms existing baselines, improving Hit@1 and Hit@2 alignment with human judgments by 24.4% and 29.7%, respectively. Our findings suggest that scientific idea evaluation can be grounded in explicit reasoning over structured scholarly experience

Retrieval components for code assistants are tuned against retrieval metrics: a configuration that raises recall@k is adopted, and downstream task success is assumed to follow. We report a controlled case study in code repair, not a new phenomenon but a deployed-flag, execution-graded instance of the known relevance-diversity and objective-mismatch tradeoff (Levy et al., 2025). On SWE-bench Verified we inject a retriever's hits as a fixed 12-slot context pack with no search tools and toggle one flag (one-chunk-per-file deduplication) on an otherwise identical stack. The flag is the higher-recall configuration (gold file present in 0.878 of served packs against 0.806 disabled), yet disabling it, trading file breadth for within-file depth, raises the single-shot resolve rate: gpt-5.6-sol +7.6pp (39.2% to 46.8%, n=500, McNemar exact p=0.0003), and a pre-registered open-weights replication any reviewer can re-run (Qwen3.6-27B, +3.6pp, n=499, p=0.0133); both survive repository-clustered inference. The gain tracks within-file anchor dose, and a random-chunk control refutes an argmax-selection artifact. We map where it holds: it reverses on a lexical BM25 retriever (-3.2pp, significant cross-paradigm interaction), is not detected under unrestricted-Read agents (a powered null), and across four languages (SWE-PolyBench, N=617) is positive but not significant (+2.6pp, p=0.056), a mapped boundary rather than a confirmed extension. Operationally, at a tight fixed budget: do not hard-deduplicate by file, and A/B packing policies against the task, not the metric the flag was tuned to.

Collegiate running in the United States generates thousands of race results annually in cross country and track and field, yet no large-scale dataset has been publicly available for research. Existing websites such as Athletic.net, MileSplit, and TFRRS host results but do not support bulk download, restricting prior analyses to ~500 performances, often skewing studies toward male athletes. We introduce the National Running Club Database (NRCD), the first openly available collegiate running dataset at scale: 143,868 approved performances from 31,351 athletes across 1,423 meets in four sports (cross country (XC), indoor and outdoor track, and road races), 36.2% women, spanning 2003-2026. Meets from August 2023 onward carry comprehensive course distance, elevation gain and loss, weather at race time, and track venue metadata (99.9% of XC rows with weather fields). NRCD is community-governed through open submission and expert approval and is maintained as a live database whose meet volume has grown yearly. We release a unified performance standardization framework that operationalizes established distance, elevation, and heat adjustments in one pipeline; XC-only validation; heat is a Hadley-band heuristic. We recommend gender-stratified modeling. On XC, full standardization lowers median within-athlete cross-meet variability by 51.1% (women) and 35.4% (men) versus raw times. We release the dataset and pipeline with a Python package `nrcd' under FAIR principles, supporting longitudinal athlete modeling, environmental-confounder studies, and gender-equity research in collegiate sport.

Privacy regulations increasingly restrict cloud processing of sensitive user data (e.g., age, gender), hindering traditional cloud-only recommendation models. To mitigate this challenge, we propose a Privacy-aware Collaborative cloud-device ads Recommendation framework (PriCoRec) which personalizes recommendations while keeping sensitive features on-device. While separating recommendation into cloud-based and on-device stages enables privacy-aware deployment, naive splitting suffers from degraded shortlist quality and inefficient on-device inference due to limited private features. We therefore design a collaborative framework that comprises a cloud-based pre-ranking stage using cloud-accessible features, and an on-device ranking stage that locally incorporates highly personalized features. We introduce a diversity regularizer to pre-ranking to improve candidate quality. Moreover, to control device power consumption and computational cost, we incorporate a cloud-guided training mechanism that enhances device model performance while keeping the model lightweight. Experiments demonstrate that the proposed framework maintains strong recommendation performance while keeping sensitive features on-device.

Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a stricter requirement: recommendations must be drawn only from a merchant's fixed catalog, without web search or unsupported product claims. In this setting, the main challenge is reliability under hard constraints: the system must satisfy user requirements, remain grounded in available inventory, and preserve preferences across multiple conversational turns. We present MACS (Multi-Agent Commerce System), a hybrid multi-agent framework for reliable conversational recommendation in fixed-catalog settings. MACS uses LLMs for language-facing tasks such as interpreting user requests, eliciting preferences, and generating responses, while correctness-critical operations, including product retrieval, hard-constraint filtering, brand exclusion, and progressive relaxation, are executed deterministically by the merchant agent. A session-persistent preference layer tracks constraints across turns, enabling consistent handling of budget overwrites and exclusion reversals. On a 140-query single-turn benchmark, MACS achieves the highest pass rate (87.1%) and perfect brand compliance (1.000). On a 10-scenario multi-turn benchmark, MACS achieves the strongest macro Pass@5 (72% vs. 56% GPT+Catalog / 52% Gemini+Catalog) with zero constraint drift. The advantage is sharpest on exclusion reversal (100% vs. 20% / 0%) and constraint accumulation (100% vs. 60% / 40%). Mean judged response quality is similar across systems (0.751 vs. 0.736). These results suggest that hybrid architectures combining deterministic constraint enforcement with session-persistent preference tracking provide stronger reliability-oriented performance than catalog-bound prompt-only baselines in the fixed-catalog merchant setting.

Public procurement represents a major economic activity, where public institutions allocate contracts to companies through competitive tendering processes. Despite its importance, this domain remains underexplored by recommender systems, largely due to the lack of publicly available datasets capturing its complexity. In this paper, we introduce TenderKG, a large-scale knowledge graph dataset constructed from French public procurement data covering the period 2021–2023. The dataset models the procurement ecosystem through heterogeneous entities, including companies, tenders, lots, and domain-specific taxonomies of work domains, connected via rich semantic and structural relations. A key specificity of this setting is that only the awarded companies are visible, resulting in sparse explicit signals of awarded interactions. To overcome this limitation, TenderKG integrates extensive side information on the actors in the French tender market and the tenders, including textual descriptions, hierarchical classifications, and geographical features, enabling the study of knowledge-aware recommendation in a highly constrained and competitive environment. We provide detailed statistics and analyses of the dataset, highlighting its structural properties, sparsity patterns, and domain-specific characteristics. We believe TenderKG opens new research directions in bidder recommendation, knowledge graph-based recommendation, competition-aware matching, and provides a valuable benchmark for evaluating methods in real-world, high-stakes decision-making scenarios.

Existing multimodal RAG methods often flatten structured documents into isolated text and image units, weakening the source organization and local text-image logic needed for faithful evidence selection and placement. We propose HAM-RAG, a Hierarchy-Aware Multimodal RAG framework for structure-faithful interleaved generation. HAM-RAG uses document hierarchy as a grounding signal across retrieval and generation, contextualizing textual and visual evidence and preserving source position and local text-image relations in the prompt. We further introduce HAM-Bench, covering Wukong, Wiki, arXiv, and Recipe across game walkthroughs, web pages, scientific papers, and step-wise recipe documents. Across multiple backbones, HAM-RAG improves the main multimodal average by 17.3% over the strongest non-hierarchical baseline. On Wukong, HAM-RAG improves Img-CBS by 24.2% over the strongest non-hierarchical baseline, demonstrating substantially better local text-image alignment. The main experiments and ablation study together demonstrate that document hierarchy is a key grounding signal for faithful image selection, placement, and local text-image alignment. These findings highlight the value of hierarchy-aware grounding for reliable multimodal assistants that generate answers faithful to the source organization, procedural structure, and local text-image evidence of structured documents, such as technical manuals, maintenance guides, and industrial SOPs. The code is available at https://github.com/MCCodeAI/HAM-RAG.git.

Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear. We combine prediction-time diagnostics with norm-based analysis of the full attention block. First, we show that SASRec-style models exhibit highly localized last-item reliance. We then find that, although self-attention aggregates contextual information, residual addition sharply shifts the full-block representation toward same-position contributions, which we term residual dominance. To probe this interpretation, we use inference-time residual scaling as a controlled diagnostic intervention. Changing the residual strength induces a monotonic trade-off between structural mixing and last-item reliance, while reducing residual strength recovers a subset of final-position misses for which representations at non-final positions already rank the ground-truth item correctly. Our results provide a structural account linking extreme last-item reliance to residual dominance at inference time. The code is publicly available.

Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the shared token space. Recent attempts have introduced Multi-Token Prediction (MTP) into this field, yet they primarily inherit its efficiency merit, leaving its potential as dense supervision unexplored. Unlocking this potential hinges on whether future behaviors qualify as informative supervision. Our analysis reveals that future behaviors carry a semantic echo of the current one far above that of random pairs, which nevertheless decays along horizons under intent transitions, making them informative yet order-dependent signals. Motivated by this, we propose EchoRec, which empowers MTP with cycle-consistent holistic preference alignment across multi-horizon for generative recommendation. It comprises two synergistic modules. Horizon-aware Preference Generation (HPG) sequentially chains lightweight auxiliary branches upon the base recommender, where each branch conditions on its predecessor to respect preference evolution. Verifiable Holistic-Preference Alignment (VHA) further consolidates them into the holistic preference and echoes it back through cycle-consistent projectors to suppress spurious alignment, with theoretical guarantees that exclude the rank-collapse form of spurious alignment under an invertible transport, enabling the holistic preference to be retained in the decoding representation. All auxiliary components serve as disposable scaffolding discarded at inference, introducing negligible online serving overhead. Extensive experiments on three datasets demonstrate the superiority of our EchoRec, together with its naturally acquired multi-item generation ability. Our code and datasets will be available upon acceptance.

Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds. These systems inherently favor shallow-content videos that are effective at attracting immediate attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising concerns about the long-term societal impact of the short-video platform. To tackle this challenge, this paper introduces a new metric, the Content Depth Score (CDS), to quantify the content depth of short videos. CDS measures the extent to which a video is expected to stimulate higher-order cognitive processes, using a seven-level scale grounded in established theories of cognitive psychology and learning. As an initial step toward this vision, we present SCOPE-Bench, the first benchmark for content-depth evaluation in short-video recommendation. Built upon a large-scale open-source short-video dataset, SCOPE-Bench provides CDS annotations for 150K videos, enabling systematic evaluation of RSs from a cognitive-content perspective. Leveraging SCOPE-Bench, we evaluate 13 representative RSs and reveal a consistent preference for shallow-content videos. Moreover, we find that these algorithms recommending cognitively deep content are only marginally better than random selection, highlighting a previously overlooked limitation of existing recommendation objectives. Our code and datasets are available at https://liweidengdavid.github.io/SCOPE-Bench/.

In RAG, while the retriever typically ranks documents by their individual relevance to the query, the generator instead produces an answer based on the retrieved documents as a whole. This paper investigates how redundancy and diversity from the retrieved document set impact the generator in terms of answer correctness. Previous work has provided a mix of findings: some showing that redundancy improves generation by reinforcing relevant information, others that LLM-based paraphrasing of the same content may be beneficial. Many of these studies did not control for confounding factors like whether the documents contained the exact answer or not, and if parametric knowledge plays a role. We conduct a carefully controlled experiment investigating three key scenarios of retrieved document sets: 1) Duplicate (exact copies of the same document), 2) Paraphrased (LLM rephrased versions of one document) and 3) Diverse (documents from different genres each containing relevant information in different forms). We control for which documents contain the answer in exact match or rephrased form. Evaluation is done with FictionalQA, a synthetic, fictional question-answer dataset that ensures the LLM generator prior knowledge cannot answer the question; the answer must come from retrieved documents. We show that duplicate redundancy and LLM paraphrasing does not significantly improve answer correctness. However, providing diverse documents is highly beneficial, improving answer correctness by 17%-47%. We further show this improvement is driven by diverse forms of document genre (news, blogs, etc.) alone and not a consequence of more relevant answer being available to generator. Our findings help to direct more attention to how new retrieval methods might improve RAG by catering to the generator preference for diversity in retrieval results.

Bluesky lets users deploy custom feeds, independently operated recommendation algorithms that the platform serves alongside thousands of others. This paper investigates how evenly these feeds treat posts with the same text. To measure this, we take repeated snapshots of the Top-50 lists that 1,366 public feeds return, and we group posts with identical text, from different authors, that were created before the same list response and closely matched in age. Exposure diverges widely inside these matched sets, which span 250 feeds: in 33% of sets, one copy appears on the list while another does not. Fixed-effects regressions show that this divergence is associated with the author's history on the specific feed. Authors new to a feed receive less exposure for the same text (-0.061 in reciprocal-rank weight), while authors whose posts the feed has returned before receive more. A new author with more followers than the competing author still loses 74% of head-to-head comparisons. Media and post-type features show no detectable association after multiple-comparison correction. These results are early evidence that access to many independent feeds is not enough to give identical texts equal exposure.

The conventional approach to cold-start recommendation addresses new users or newly introduced items. Bluesky custom feeds create a different setting: independently operated feeds filter content from a shared public stream. In this setting, newly published posts are the cold-start objects, while the feeds serve as candidates. We propose a cold-start routing task in which a newly ingested public post is the query and all rankable feeds in the monitored panel are ranked according to whether each will subsequently return it. We build a still-evolving collect-first, label-later benchmark dataset. The collected dataset covers a fixed panel of 5,000 monitored feeds and contains 17.804 million public posts, 1.865 million observable post–feed return records, and 625,083 valid feed polls. The labels record whether a post is observed among a feed's AppView Top-50 results in at least one poll during the 24 hours after publication. The current experiments use two disjoint 24-hour test folds, each paired with a 24-hour training window and separated by a 24-hour outcome-availability gap. Evaluation is conditional on the 602,186 test posts that have at least one positive observed label and satisfy the metric eligibility criteria; these posts account for 9.04% of all 6,661,658 test posts. Across the two folds, LambdaRank achieves the best equal-fold mean values among the evaluated models: 0.7361 for capped Recall@10, 0.6127 for NDCG@10, and 0.7749 for Hit@10.

PLEASE CHECK AND REFER TO THE PUBLISHED VERSION OF THIS PAPER ON https://doi.org/10.5334/tismir.357 This paper presents the MPB Corpus, a dataset of Brazilian Popular Music (Musica Popular Brasileira, MPB) comprising derived symbolic annotations for 500 pieces across four musical parameters – melodic contour, melodic rhythm, harmony, and the melody-harmony relationship – making it the most comprehensive dataset to date for computational musicology of Brazilian music. It is released under a CC-BY-4.0 license in an open, machine-readable tabular format, with documentation and reproducible analysis code. Because the annotations were derived from copyrighted musical scores, the corpus contains no audio recordings or score-level representations such as MIDI or MusicXML; it nonetheless provides a reusable resource for MIR research on a culturally significant repertoire that remains underrepresented in existing datasets. To support the encoding process, we introduce analytical models for capturing rhythmic and melodic information, along with tailored visualizations and summary metrics. Finally, we present a brief exploratory analysis illustrating the dataset's potential for formulating and addressing musicological questions about the genre.

Listwise language-model rerankers often disagree across equivalent candidate permutations. Finite instability diagnostics are therefore used to motivate additional sampling, aggregation, or selective computation. But an association with a validation statistic that reuses the probe views need not isolate predictive information about unseen permutations. Shared measurements can induce classical part-whole association. We study how this affects claims that a finite-view instability score predicts unseen permutations. We derive the exact finite-view decomposition and prospectively compare zero, one, and two reused views, including a fully disjoint four-view target. The study covers two pinned 7B model families and two recommendation datasets, with controlled lists for signed offline analysis and untouched retriever lists for target-free replication. On the four controlled blocks, fully disjoint correlations are weak or heterogeneous (-0.061 to 0.281), whereas reusing both probe views yields 0.600 to 0.718; all paired contrasts are large (0.436 to 0.661) and Holm-significant. The overlap effect is positive in all four untouched-list blocks. Increasing the probe from two to four views clearly improves disjoint reliability in only one block. Moreover, the probe predicts aggregation-movement magnitude (Spearman rho = 0.142 to 0.426) but not stable signed target benefit, and 7 of 12 fixed-fraction probe-routing points are strictly dominated at measured cost. Thus, when the intended estimand is predictive information about unseen perturbation behavior, validation targets must be observation-disjoint from the probe to isolate that information; signed utility and cost-sensitive decisions remain separate questions.

Rerankers are increasingly evaluated through downstream language-model answers. This raises a retrieval-measurement question: if only the reader's answer interface changes, should we reach the same conclusion about BM25 versus BGE-v2-m3? We prospectively audit their claim-paired effect on RAGuard and FEVER with four readers. Retrieval policies, evidence, claims, and context depth remain fixed while semantic-to-label binding, A/B versus X/Y vocabulary, and option order form eight task-equivalent interfaces. We ask whether the estimated retrieval-policy effect, its ordering, or selection value changes. None of the six confirmatory settings showed statistically certified interface variation above the prespecified 0.015 materiality threshold, and none showed a certified reversal of the BM25-BGE ordering. Selector disagreement reaches 33.5% in one environment, yet none of eight environments establishes the prespecified material held-out value difference. These results do not support broad replicated instability, but they do not prove universal invariance: five settings remain too uncertain to satisfy the prespecified higher-order equivalence condition. They show why retrieval evaluations should separate policy level, interface stability, policy ordering, and selection value. When stability is unverified, a uniform average over the enumerated interfaces with explicit variation bounds avoids privileging one interface.

Conversational advertising aims to deliver useful ads within multi-turn assistant interactions. Unlike conventional query-based advertising, where the user's intent is often expressed in a short standalone query, conversational ads must infer latent commercial intent from the current user query, the assistant response, and dialogue history while also deciding whether an ad would be helpful rather than intrusive. We propose AdsWorldEngine, an agentic framework for conversational advertising. AdsWorldEngine uses an Opportunity Gate to determine whether ads should be shown, an Orchestrator to generate commercial intents, call advertising tools, and construct a top-3 ad slate, and an Evaluator to score delivered ads for offline optimization. The central contribution is an iterative actor-tool training procedure: we first train the Orchestrator with supervised fine-tuning and agentic reinforcement learning, then use high- and low-reward rollouts to construct preference data to train tools. This creates a self-improving loop in which the system learns not only how to use advertising tools, but also how to improve them from rewarded behavior. To support subjective production decisions, we introduce label grounded judgment modeling, which trains judgment models from human labels collected under explicit guidelines. It enriches labels with thinking traces, filters inconsistent rationales through reflection, and further optimizes binary judgments with a cost sensitive GRPO variant that preserves asymmetric reward gaps. Offline, AdsWorldEngine improves diversity by 60% and relevance by 80% over the current production ad delivery system. In an online A/B test, it increases RPM by 22% and ads coverage by 74%.